Fall

Twitter Profile Recommendation System Based on Explicit User Feedback

With the rapid development in technology and easy access to information, a community of “makers” emerged. There is a project called Open Maker that aims to bring together the makers and manufacturers in Europe. As a submodule of the project, we developed a Twitter Account Recommendation System based on explicit user feedback. Since our setting was rather unique, we used several methods to improve the prediction performance, compared the results and assessed possible shortcomings.

eBloc Blockchain Voting

Blockchain is a linked list of cryptographically secured blocks of information that can be maintained on a peer-to-peer network. Its cryptographic and decentralized nature provides blockchain applications immutability, corruption & tamper proofness, security and fault tolerance which make elections an ideal application of blockchain technologies. Ethereum, a computing platform that provides a Turing-complete virtual machine on blockchain networks lets users deploy and run applications called smart contracts.

Android Race Detection Tool

The main goal of this two semester project is to create a race detection tool for Android applications, without using an instrumented operating system.

Load Balancing in ICN

Information-Centric Networking is still an incomplete paradigm which introduces a large variety of new topics and approaches over the traditional networking. Since it is a relatively new concept which promises for easier and faster data access many aspects of it have been studied intensely in recent years. Nonetheless, load balancing is one of the less focused but high potency, open-ended areas. The aim of this project is to present an alternative technique to load balancing in the domain of pre-suggested routing method LSCR (Link State Content Routing).

Adapting Full Body Synergies

Boğaziçi University Department of Computer Engineering BSc Graduation Project (491) Fall 2017 Adapting Full Body Synergies project is an analysis on humans’ way of controlling motor movements. Instead of controlling all degrees of freedom separately, brain tends to use combinations of \textit{motor synergies} to perform a movement, which is more efficient. After conforming this capability of humans, the synergies are extracted to perform further analysis on human learning. First, the data from a periodic movement, walking, is collected as reference.

Gesture Alignment Using Canonical Time Warping

In this project, we are interested with the problem of aligning features of human motions and gestures. There are variations in subjects’ characteristics, style, and speed in hand, body, and facial gestures. We try to minimize effects of those variations by a pre-alignment step. Canonical Time Warping (CTW) and Generalized Canonical Time Warping (GTW) are claimed to give better results for human motion alignment than alternative methods. Our aim is to analyze mathematical foundations of GTW, fine tune its parameters for sign language alignment, and find the best setup for GTW to work.

Clean Code Analysis for C++

Most developers are unwilling to spend time on writing a clean code because they want their code to run as soon as possible. For this reason, they immediately want to jump into the coding process. Of course, this is not a good engineering approach; but, let us imagine an ordinary developer and his/her behaviors. Because of their desire to see their creation as soon as possible, they don't have a proper preparation period and they ignore how clean and understandable their code is while trying to have a working implementation.

Search form

Main Menu

Twitter Profile Recommendation System Based on Explicit User Feedback

eBloc Blockchain Voting

Android Race Detection Tool

Load Balancing in ICN

Adapting Full Body Synergies

Gesture Alignment Using Canonical Time Warping

Clean Code Analysis for C++

CmpE 482 Sp.Tp. Numerical Linear Algebra and Its Applications 2017 Fall

CmpE 700 Graduate Seminar 2017 Fall

SWE 599 Project 2017 Fall

Pages

Contact us

Connect with us